Class RainbowDQNOptions<T>

Namespace

AiDotNet.Models.Options

Assembly

AiDotNet.dll

Configuration options for Rainbow DQN agent.

public class RainbowDQNOptions<T> : ReinforcementLearningOptions<T>

Type Parameters

T

The numeric type used for calculations.

Inheritance

object

ReinforcementLearningOptions<T>

RainbowDQNOptions<T>

Inherited Members

ReinforcementLearningOptions<T>.LearningRate

ReinforcementLearningOptions<T>.DiscountFactor

ReinforcementLearningOptions<T>.LossFunction

ReinforcementLearningOptions<T>.Seed

ReinforcementLearningOptions<T>.BatchSize

ReinforcementLearningOptions<T>.ReplayBufferSize

ReinforcementLearningOptions<T>.TargetUpdateFrequency

ReinforcementLearningOptions<T>.UsePrioritizedReplay

ReinforcementLearningOptions<T>.EpsilonStart

ReinforcementLearningOptions<T>.EpsilonEnd

ReinforcementLearningOptions<T>.EpsilonDecay

ReinforcementLearningOptions<T>.WarmupSteps

ReinforcementLearningOptions<T>.MaxGradientNorm

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

Rainbow DQN combines six extensions to DQN:

1. Double Q-learning: Reduces overestimation bias
2. Dueling networks: Separates value and advantage streams
3. Prioritized replay: Samples important experiences more frequently
4. Multi-step learning: Uses n-step returns for better credit assignment
5. Distributional RL: Learns full distribution of returns (C51)
6. Noisy networks: Parameter noise for exploration

Properties

ActionSize

public int ActionSize { get; init; }

Property Value

int

AdvantageStreamLayers

public List<int> AdvantageStreamLayers { get; init; }

Property Value

List<int>

NSteps

public int NSteps { get; init; }

Property Value

int

NoisyNetSigma

public double NoisyNetSigma { get; init; }

Property Value

double

NumAtoms

public int NumAtoms { get; init; }

Property Value

int

Optimizer

The optimizer used for updating network parameters. If null, Adam optimizer will be used by default.

public IOptimizer<T, Vector<T>, Vector<T>>? Optimizer { get; init; }

Property Value

IOptimizer<T, Vector<T>, Vector<T>>

PriorityAlpha

public double PriorityAlpha { get; init; }

Property Value

double

PriorityBeta

public double PriorityBeta { get; init; }

Property Value

double

PriorityBetaIncrement

public double PriorityBetaIncrement { get; init; }

Property Value

double

PriorityEpsilon

public double PriorityEpsilon { get; init; }

Property Value

double

SharedLayers

public List<int> SharedLayers { get; init; }

Property Value

List<int>

StateSize

public int StateSize { get; init; }

Property Value

int

UseDistributional

public bool UseDistributional { get; init; }

Property Value

bool

UseNoisyNetworks

public bool UseNoisyNetworks { get; init; }

Property Value

bool

VMax

public double VMax { get; init; }

Property Value

double

VMin

public double VMin { get; init; }

Property Value

double

ValueStreamLayers

public List<int> ValueStreamLayers { get; init; }

Property Value

List<int>